Software Engineer, RL Data
San Francisco, CA | New York City, NY
Posted 16d ago
Job Location
San Francisco, CA | New York City, NY
Tech Stack
Remote Work Policy
On-site
Categories
Applied AI Engineer
About the job
Anthropic is building reliable, interpretable, and steerable AI systems to be safe and beneficial for users and society. This senior, foundational role on a new team involves making key architectural decisions and shaping initial development. The work is hands-on and varied, encompassing pipeline and infrastructure engineering, prompt tuning, and supporting research teams. The RL Data team focuses on building systems for high-quality reinforcement learning data for Claude, including data collection pipelines, human feedback tooling, execution environments, and quality assurance to ensure trustworthy training data at scale. The goal is to enhance Claude's capabilities in real-world tasks, particularly in AI safety research and beneficial AI deployments.
Responsibilities
- Own significant parts of the stack end-to-end, from architecture to operational execution.
- Build data collection pipelines, analyze transcripts, and iterate on prompts, evaluations, and grading for optimal output.
- Develop and enhance QA frameworks to detect reward hacking and ensure environment quality.
- Create interfaces to streamline human data collection for providers.
- Harden execution environments with sandboxing, snapshotting, and tool coverage for training scale.
- Collaborate with user teams, domain experts, operations, security, and compliance partners for system rollout.
Requirements
- Proven track record of owning major projects end-to-end in fast-paced, ambiguous environments.
- Ability to lead and inspire others, plan workstreams, collaborate with stakeholders, and proactively manage blockers.
- Strong software engineering skills in a modern programming language (Python and TypeScript preferred, with ability to learn new tools quickly).
- Familiarity with Docker, Kubernetes, and common cloud infrastructure is a plus.
- Experience using AI tools in daily work.
- Commitment to the societal impacts of AI work.